A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
The study characterizes sets for which one-layer neural networks are positive.
Law derived for neural networks with sparse connections.
Gradient descent fails to learn simple neural networks efficiently.
Generative adversarial networks (GANs) are a widely used framework for learning generative models. Wasserstein GANs (WGANs), one of the most successful variants of GANs, require solving a minmax optimization problem to global optimality, but are in practice successfully trained using stochastic gradient descent-ascent.…
Randomly initialized neural networks can linearly separate arbitrary sets.
One-layer transformers can't solve induction heads task efficiently.
The study estimates the expressiveness of GCNs with bounds on the number of linear regions.
Layer-wise networks have a closed-form solution and a stopping criterion.
Layer-wise networks have a closed-form solution and a stopping criterion.
It is often hypothesized that a crucial role for recurrent connections in the brain is to constrain the set of possible response patterns, thereby shaping the neural code. This implies the existence of neural codes that cannot arise solely from feedforward processing. We set out to find such codes in the context of one…
Neural networks are dense among Lipschitz functions with fixed Lipschitz constant.
One LN layer stabilizes neural network extrapolation.
Study on calibration and consistency of adversarial surrogate losses.
Deep networks without non-linearities are equivalent to shallow ones.
While the optimization problem behind deep neural networks is highly non-convex, it is frequently observed in practice that training deep networks seems possible without getting stuck in suboptimal points. It has been argued that this is the case as all local minima are close to being globally optimal. We show that thi…
Study explores how neural networks and Transformers learn modular arithmetic with multiple inputs.
Paper quantifies MEV on L2 networks, finding significant amounts on Polygon.
The R package abn is designed to fit additive Bayesian models to observational datasets. It contains routines to score Bayesian networks based on Bayesian or information theoretic formulations of generalized linear models. It is equipped with exact search and greedy search algorithms to select the best network. It supp…
This study analyzes how one-layer transformers learn regular language recognition tasks.
Inspired by coarse-graining approaches used in physics, we show how similar algorithms can be adapted for data. The resulting algorithms are based on layered tree tensor networks and scale linearly with both the dimension of the input and the training set size. Computing most of the layers with an unsupervised algorith…
In this work we propose a new deep learning tool called deep dictionary learning. Multi-level dictionaries are learnt in a greedy fashion, one layer at a time. This requires solving a simple (shallow) dictionary learning problem, the solution to this is well known. We apply the proposed technique on some benchmark deep…
Improved bounds on neural network regions using activation histograms.
Analytical solution found for a three-layer network with a specific activation function.
Study on feature learning dynamics in infinite-depth neural networks, focusing on ResNets.
We consider the problem of estimating the parameters of a -dimensional rectified Gaussian distribution from i.i.d. samples. A rectified Gaussian distribution is defined by passing a standard Gaussian distribution through a one-layer ReLU neural network. We give a simple algorithm to estimate the parameters (i.e., th…
We introduce a new method for training deep Boltzmann machines jointly. Prior methods require an initial learning pass that trains the deep Boltzmann machine greedily, one layer at a time, or do not perform well on classifi- cation tasks.
An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem through the lens of axiomatic attribution of neural networks. Our theory is grounded in the recent work, Integrated Gradients (IG), in axiomatical…
Deep neural networks (DNNs) may outperform human brains in complex tasks, but the lack of transparency in their decision-making processes makes us question whether we could fully trust DNNs with high stakes problems. As DNNs' operations rely on a massive number of both parallel and sequential linear/nonlinear computati…
We describe \textit{deep exponential families} (DEFs), a class of latent variable models that are inspired by the hidden structures used in deep neural networks. DEFs capture a hierarchy of dependencies between latent variables, and are easily generalized to many settings through exponential families. We perform infere…
Paper proposes knockoff-based methods to simplify deep neural networks by controlling false discovery rates.
Transformers can learn optimal variable selection in group-sparse classification.
RNNs solve modular addition tasks using low rank and sparse Fourier structures.
We study deep neural networks with polynomial activations, particularly their expressive power. For a fixed architecture and activation degree, a polynomial neural network defines an algebraic map from weights to polynomials. The image of this map is the functional space associated to the network, and it is an irreduci…
Despite their great success in recent years, deep neural networks (DNN) are mainly black boxes where the results obtained by running through the network are difficult to understand and interpret. Compared to e.g. decision trees or bayesian classifiers, DNN suffer from bad interpretability where we understand by interpr…
Overparameterized Neural Networks (NN) display state-of-the-art performance. However, there is a growing need for smaller, energy-efficient, neural networks tobe able to use machine learning applications on devices with limited computational resources. A popular approach consists of using pruning techniques. While thes…
Neural networks with low-precision weights and activations offer compelling efficiency advantages over their full-precision equivalents. The two most frequently discussed benefits of quantization are reduced memory consumption, and a faster forward pass when implemented with efficient bitwise operations. We propose a t…
A toolkit for path-norms enhances neural network generalization bounds.
Transformers excel at sparse token selection, surpassing FCNs in both worst and average cases.
This paper compares Transformers and RNNs in various tasks, showing size differences.
We consider the problem of training generative models with a Generative Adversarial Network (GAN). Although GANs can accurately model complex distributions, they are known to be difficult to train due to instabilities caused by a difficult minimax optimization problem. In this paper, we view the problem of training GAN…
Analytical method finds deeper optima in two-layer ReLU networks.
We present a general framework for training deep neural networks without backpropagation. This substantially decreases training time and also allows for construction of deep networks with many sorts of learners, including networks whose layers are defined by functions that are not easily differentiated, like decision t…
Paper studies the expressivity of Convolutional Neural Networks (CNNs).
Study shows efficient neural network approach for stochastic bandits.
We give a polynomial-time algorithm for learning neural networks with one layer of sigmoids feeding into any Lipschitz, monotone activation function (e.g., sigmoid or ReLU). We make no assumptions on the structure of the network, and the algorithm succeeds with respect to {\em any} distribution on the unit ball in …
Understanding deep neural networks is a major research objective with notable experimental and theoretical attention in recent years. The practical success of excessively large networks underscores the need for better theoretical analyses and justifications. In this paper we focus on layer-wise functional structure and…
An efficient way to learn deep density models that have many layers of latent variables is to learn one layer at a time using a model that has only one layer of latent variables. After learning each layer, samples from the posterior distributions for that layer are used as training data for learning the next layer. Thi…
It is well known that (stochastic) gradient descent has an implicit bias towards flat minima. In deep neural network training, this mechanism serves to screen out minima. However, the precise effect that this has on the trained network is not yet fully understood. In this paper, we characterize the flat minima in linea…